mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-29 11:24:19 +00:00
7c1e3daa75
# What does this PR do? - Fix broken pytest for meta-reference's agents - Safety model needs to be registered to a different provider id from inference model in order to be recognized ## Test Plan ``` torchrun $CONDA_PREFIX/bin/pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "meta_reference" --safety-shield meta-llama/Llama-Guard-3-1B --inference-model meta-llama/Llama-3.1-8B-Instruct ``` **Before** <img width="845" alt="image" src="https://github.com/user-attachments/assets/83818fe1-2179-4e9c-a753-bf1472a2f01d" /> **After** <img width="851" alt="image" src="https://github.com/user-attachments/assets/1cf8124b-14e2-47bf-80fd-ef8b4b3f6fd9" /> **Other test not broken** ``` pytest -v -s llama_stack/providers/tests/agents/test_agents.py -m "together" --safety-shield meta-llama/Llama-Guard-3-8B --inference-model meta-llama/Llama-3.1-405B-Instruct-FP8 ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
122 lines
3.9 KiB
Python
122 lines
3.9 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import tempfile
|
|
|
|
import pytest
|
|
import pytest_asyncio
|
|
|
|
from llama_stack.apis.models import ModelInput, ModelType
|
|
from llama_stack.distribution.datatypes import Api, Provider
|
|
|
|
from llama_stack.providers.inline.agents.meta_reference import (
|
|
MetaReferenceAgentsImplConfig,
|
|
)
|
|
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
|
from ..conftest import ProviderFixture, remote_stack_fixture
|
|
|
|
|
|
def pick_inference_model(inference_model):
|
|
# This is not entirely satisfactory. The fixture `inference_model` can correspond to
|
|
# multiple models when you need to run a safety model in addition to normal agent
|
|
# inference model. We filter off the safety model by looking for "Llama-Guard"
|
|
if isinstance(inference_model, list):
|
|
inference_model = next(m for m in inference_model if "Llama-Guard" not in m)
|
|
assert inference_model is not None
|
|
return inference_model
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def agents_remote() -> ProviderFixture:
|
|
return remote_stack_fixture()
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def agents_meta_reference() -> ProviderFixture:
|
|
sqlite_file = tempfile.NamedTemporaryFile(delete=False, suffix=".db")
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="meta-reference",
|
|
provider_type="inline::meta-reference",
|
|
config=MetaReferenceAgentsImplConfig(
|
|
# TODO: make this an in-memory store
|
|
persistence_store=SqliteKVStoreConfig(
|
|
db_path=sqlite_file.name,
|
|
),
|
|
).model_dump(),
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
AGENTS_FIXTURES = ["meta_reference", "remote"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def agents_stack(request, inference_model, safety_shield):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in ["inference", "safety", "memory", "agents"]:
|
|
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
|
|
providers[key] = fixture.providers
|
|
if key == "inference":
|
|
providers[key].append(
|
|
Provider(
|
|
provider_id="agents_memory_provider",
|
|
provider_type="inline::sentence-transformers",
|
|
config={},
|
|
)
|
|
)
|
|
if fixture.provider_data:
|
|
provider_data.update(fixture.provider_data)
|
|
|
|
inference_models = (
|
|
inference_model if isinstance(inference_model, list) else [inference_model]
|
|
)
|
|
|
|
# NOTE: meta-reference provider needs 1 provider per model, lookup provider_id from provider config
|
|
model_to_provider_id = {}
|
|
for provider in providers["inference"]:
|
|
if "model" in provider.config:
|
|
model_to_provider_id[provider.config["model"]] = provider.provider_id
|
|
|
|
models = []
|
|
for model in inference_models:
|
|
if model in model_to_provider_id:
|
|
provider_id = model_to_provider_id[model]
|
|
else:
|
|
provider_id = providers["inference"][0].provider_id
|
|
|
|
models.append(
|
|
ModelInput(
|
|
model_id=model,
|
|
model_type=ModelType.llm,
|
|
provider_id=provider_id,
|
|
)
|
|
)
|
|
|
|
models.append(
|
|
ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
model_type=ModelType.embedding,
|
|
provider_id="agents_memory_provider",
|
|
metadata={"embedding_dimension": 384},
|
|
)
|
|
)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[Api.agents, Api.inference, Api.safety, Api.memory],
|
|
providers,
|
|
provider_data,
|
|
models=models,
|
|
shields=[safety_shield] if safety_shield else [],
|
|
)
|
|
return test_stack
|